Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 9183
    Prev
    Next
    INDEX
    Explanations

    words related to irony

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "irony" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tests
    -0.81
    league
    -0.79
    liquid
    -0.76
    eding
    -0.76
    eder
    -0.76
    hani
    -0.74
    gur
    -0.73
    erto
    -0.72
    aver
    -0.71
    aah
    -0.71
    POSITIVE LOGITS
     irony
    1.21
     ironic
    1.16
     paradox
    0.89
     twist
    0.88
     juxtap
    0.85
     ironically
    0.83
     sarc
    0.83
    netflix
    0.81
     mockery
    0.81
     Osw
    0.80
    Activations Density 0.012%

    No Known Activations